Selective Correlation Based Knowledge Distillation for Ground Reaction Force Estimation

2026-04-27

AI Summary

This study addresses the challenge of estimating ground reaction forces (GRF) using wearable insole sensors, which are prone to noise interference, while high-accuracy deep learning models incur excessive computational costs that hinder deployment on portable devices. To overcome this trade-off, the authors propose a Selective Correlation-based Knowledge Distillation (SCKD) method that enables efficient knowledge transfer from a complex teacher network to a lightweight student network by constructing temporal feature correlation graphs. The approach introduces a novel temporally aware selective feature correlation mechanism that not only enhances model interpretability but also significantly reduces computational complexity. Experimental results demonstrate that SCKD consistently achieves high estimation accuracy across varying walking speeds and window sizes while substantially lowering resource consumption, outperforming existing GRF estimation methods.

Abstract

Wearable sensor-based human gait analysis holds great promise in healthcare, rehabilitation, clinical diagnosis and monitoring, and sports activities. Specifically, ground reaction force (GRF) provides essential insights into the body's interaction with the ground during movement and is typically measured using instrumented treadmills equipped with force plates. However, such equipment is expensive and restricted to laboratory environments. To enable a more portable solution, wearable insole sensors have been used to measure GRF. These sensors, however, are prone to noise and external interference, which reduces measurement accuracy. Deep learning methodologies could be adopted to address these issues, but they often require significant computing resources to achieve high accuracy, limiting their applicability for real-time analysis on portable devices. To overcome these limitations, we propose Selective Correlation Based Knowledge Distillation (SCKD) for estimating GRF from data collected by insole sensors. Our proposed method utilizes selected features considering temporal characteristics in the process of extracting correlation maps for knowledge transfer, enhancing interpretability and mitigating issues in high dimensional data processing. We demonstrate the effectiveness of the compact models generated by our distillation framework through comparison with existing methods. Various configurations of teacher-student architectures and training approaches are examined based on multiple evaluation criteria, utilizing data collected at different walking speeds and with different window sizes. Experimental results confirm that our approach outperforms existing methods in estimating GRF from wearable insole sensor data. Therefore, our approach offers a reliable and resource-efficient solution for human gait analysis.

Problem

• ground reaction force
• wearable sensors
• knowledge distillation
• gait analysis
• noise interference

Innovation

• Selective Correlation
• Knowledge Distillation
• Ground Reaction Force Estimation
• Wearable Sensors
• Temporal Feature Selection